Offensive Security Researcher, SEAR

Apples Security Engineering u0026 Architecture (SEAR) organization is responsible for the security of all Apple products. Passionate about safeguarding our users we lead with offence proactively uncovering and eliminating vulnerabilities before attackers ever get the AI systems become deeply integrated into operating systems developer tools and user experiences they introduce entirely new attack surfaces vulnerable to prompt injection agentic privilege escalation data exfiltration and AI-assisted exploitation at unprecedented you have the creativity and determination to break these systems Join us and help secure the next generation of intelligent platforms used by billions of people.

In this role you will identify and exploit vulnerabilities in AI-powered features and agentic systems across Apple platforms. The AI systems themselves are the attack surface. You will help to build offensive capabilities against autonomous systems and anticipate how adversaries may exploit AI enabled systems in the will join a team working with world-class offensive security researchers. The work is critical directly shapes the security posture of will conduct offensive research into AI-specific attack classes including prompt injection agentic data exfiltration and lateral movement persistence mechanisms in AI workflows AI-assisted vulnerability discovery and exploitation.

Solid grounding in common vulnerability classes (memory corruption logic flaws auth bypass)nProven experience in security research vulnerability discovery or offensive security (e.g. browsers 0-click messaging systems distributed systems or AI platforms)nStrong understanding of modern AI/LLM systems and their failure modes (e.g. prompt injection data exfiltration model misuse)nExperience applying AI/ML tools (e.g. LLMs agents) to automate or augment security research workflows

Experience attacking or defending agentic systems (multi-step AI workflows tool-using agents MCP-style integrations)nFamiliarity with prompt injection techniques obfuscation (e.g. encoding-based bypasses) and model manipulation strategiesnExperience building or evaluating AI-driven vulnerability discovery pipelinesnUnderstanding of browser-based AI integrations and risks (e.g. agentic browsing data boundary violations)nKnowledge of capability-based security models or policy enforcement systems for AI agentsnExperience with reverse engineering and low-level systems (IDA Ghidra LLDB)nProficiency in one or more: Python C/C Swift Objective-CnFamiliarity with Apple platforms (iOS macOS) and their security architecture